INDEX

Explanations

phrases indicating similarity or uniformity

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

yer

-0.15

acle

-0.15

 indefinite

-0.14

 Alley

-0.14

 Shelter

-0.14

oge

-0.14

azz

-0.14

pr

-0.13

 unlimited

-0.13

POSITIVE LOGITS

Across

0.18

Uniform

0.17

cir

0.16

 Uniform

0.16

modulo

0.15

 ÑģÐ¾Ð¿

0.15

_FOREACH

0.15

 Across

0.15

 uniform

0.14

Ø®ÙĪ

0.14

Activations Density 0.144%

phrases indicating similarity or uniformity

No Comments

No Known Activations